Using vehicle data as a surrogate for highway accident data

Abstract

Many studies have tried to use the surrogate safety measures (SSM) estimated from the microscopic traffic simulations. However, it is difficult to adopt these developed SSM to reflect real-world traffic conditions when the developed network in the simulation is not calibrated and validated accordingly. This paper proposed a method to develop the pattern-based surrogate safety measure (PSSM) using individual vehicle trajectory data. The PSSM can be estimated based on the pattern of hazardous driving behaviour (HDB). Using digital tacho graph data collected from the commercial vehicles, HDB patterns were obtained. Various PSSMs were developed and validated with the observed crash data using Random Forest. Then, the surrogate safety performance function was estimated based on the frequency of HDB. To enhance model performance, machine learning and data mining techniques were applied. The results show that sudden deceleration, sudden lane change, sudden overtaking and sudden U-turn are related to traffic crashes during HDB. The results also show that high potential for safety improvement was identified in the road section linking the urban and suburban areas. The findings from this study can provide new approach to adopt real-time individual vehicle trajectory data to evaluate safety performance of network levels.